xhumanoid commented on code in PR #5923:
URL: https://github.com/apache/datafusion-comet/pull/5923#discussion_r4163379079
##########
spark/src/test/scala/org/apache/comet/CometCodegenSuite.scala:
##########
@@ -1143,6 +1143,24 @@ class CometCodegenSuite
checkSparkAnswerAndOperator(df)
}
+ test("a scalar subquery inside the dispatched subtree falls back to Spark") {
+ // The dispatcher serializes the tree at plan time, but a subquery's
`result` is populated by
+ // the surrounding operator's `waitForSubqueries` at execution time. The
deserialized copy on
+ // the executor therefore has no result, and `ScalarSubquery.doGenCode`
used to fail the kernel
+ // compile with "Subquery ... has not finished" -- a runtime failure,
after the plan had already
+ // committed to the kernel. `canHandle` now refuses it, so the operator
falls back cleanly.
+ spark.udf.register("addOne", (i: Int) => i + 1)
+ withTable("t", "t2") {
+ sql("CREATE TABLE t (x INT) USING parquet")
+ sql("INSERT INTO t VALUES (1), (2), (3), (4), (5)")
+ sql("CREATE TABLE t2 (v INT) USING parquet")
+ sql("INSERT INTO t2 VALUES (2), (4)")
+ assertNoCodegen {
+ checkSparkAnswer(sql("SELECT addOne((SELECT max(v) FROM t2)) AS r FROM
t"))
+ }
+ }
+ }
+
test("ScalaUDF composed with reused scalar subquery across projection and
filter") {
Review Comment:
sure, will update it
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
